比较提交
合并到: unity-tech-cn:main
unity-tech-cn:/main
unity-tech-cn:/develop-generalizationTraining-TrainerController
unity-tech-cn:/tag-0.2.0
unity-tech-cn:/tag-0.2.1
unity-tech-cn:/tag-0.2.1a
unity-tech-cn:/tag-0.2.1c
unity-tech-cn:/tag-0.2.1d
unity-tech-cn:/hotfix-v0.9.2a
unity-tech-cn:/develop-gpu-test
unity-tech-cn:/0.10.1
unity-tech-cn:/develop-pyinstaller
unity-tech-cn:/develop-horovod
unity-tech-cn:/PhysXArticulations20201
unity-tech-cn:/importdocfix
unity-tech-cn:/develop-resizetexture
unity-tech-cn:/hh-develop-walljump_bugfixes
unity-tech-cn:/develop-walljump-fix-sac
unity-tech-cn:/hh-develop-walljump_rnd
unity-tech-cn:/tag-0.11.0.dev0
unity-tech-cn:/develop-pytorch
unity-tech-cn:/tag-0.11.0.dev2
unity-tech-cn:/develop-newnormalization
unity-tech-cn:/tag-0.11.0.dev3
unity-tech-cn:/develop
unity-tech-cn:/release-0.12.0
unity-tech-cn:/tag-0.12.0-dev
unity-tech-cn:/tag-0.12.0.dev0
unity-tech-cn:/tag-0.12.1
unity-tech-cn:/2D-explorations
unity-tech-cn:/asymm-envs
unity-tech-cn:/tag-0.12.1.dev0
unity-tech-cn:/2D-exploration-raycast
unity-tech-cn:/tag-0.12.1.dev1
unity-tech-cn:/release-0.13.0
unity-tech-cn:/release-0.13.1
unity-tech-cn:/plugin-proof-of-concept
unity-tech-cn:/release-0.14.0
unity-tech-cn:/hotfix-bump-version-master
unity-tech-cn:/soccer-fives
unity-tech-cn:/release-0.14.1
unity-tech-cn:/bug-failed-api-check
unity-tech-cn:/test-recurrent-gail
unity-tech-cn:/hh-add-icons
unity-tech-cn:/release-0.15.0
unity-tech-cn:/release-0.15.1
unity-tech-cn:/hh-develop-all-posed-characters
unity-tech-cn:/internal-policy-ghost
unity-tech-cn:/distributed-training
unity-tech-cn:/hh-develop-improve_tennis
unity-tech-cn:/test-tf-ver
unity-tech-cn:/release_1_branch
unity-tech-cn:/tennis-time-horizon
unity-tech-cn:/whitepaper-experiments
unity-tech-cn:/r2v-yamato-linux
unity-tech-cn:/docs-update
unity-tech-cn:/release_2_branch
unity-tech-cn:/exp-mede
unity-tech-cn:/sensitivity
unity-tech-cn:/release_2_verified_load_fix
unity-tech-cn:/test-sampler
unity-tech-cn:/release_2_verified
unity-tech-cn:/hh-develop-ragdoll-testing
unity-tech-cn:/origin-develop-taggedobservations
unity-tech-cn:/MLA-1734-demo-provider
unity-tech-cn:/sampler-refactor-copy
unity-tech-cn:/PhysXArticulations20201Package
unity-tech-cn:/tag-com.unity.ml-agents_1.0.8
unity-tech-cn:/release_3_branch
unity-tech-cn:/github-actions
unity-tech-cn:/release_3_distributed
unity-tech-cn:/fix-batch-tennis
unity-tech-cn:/distributed-ppo-sac
unity-tech-cn:/gridworld-custom-obs
unity-tech-cn:/hw20-segmentation
unity-tech-cn:/hh-develop-gamedev-demo
unity-tech-cn:/active-variablespeed
unity-tech-cn:/release_4_branch
unity-tech-cn:/fix-env-step-loop
unity-tech-cn:/release_5_branch
unity-tech-cn:/fix-walker
unity-tech-cn:/release_6_branch
unity-tech-cn:/hh-32-observation-crawler
unity-tech-cn:/trainer-plugin
unity-tech-cn:/hh-develop-max-steps-demo-recorder
unity-tech-cn:/hh-develop-loco-walker-variable-speed
unity-tech-cn:/exp-0002
unity-tech-cn:/experiment-less-max-step
unity-tech-cn:/hh-develop-hallway-wall-mesh-fix
unity-tech-cn:/release_7_branch
unity-tech-cn:/exp-vince
unity-tech-cn:/hh-develop-gridsensor-tests
unity-tech-cn:/tag-release_8_test0
unity-tech-cn:/tag-release_8_test1
unity-tech-cn:/release_8_branch
unity-tech-cn:/docfix-end-episode
unity-tech-cn:/release_9_branch
unity-tech-cn:/hybrid-action-rewardsignals
unity-tech-cn:/MLA-462-yamato-win
unity-tech-cn:/exp-alternate-atten
unity-tech-cn:/hh-develop-fps_game_project
unity-tech-cn:/fix-conflict-base-env
unity-tech-cn:/release_10_branch
unity-tech-cn:/exp-bullet-hell-trainer
unity-tech-cn:/ai-summit-exp
unity-tech-cn:/comms-grad
unity-tech-cn:/walljump-pushblock
unity-tech-cn:/goal-conditioning
unity-tech-cn:/release_11_branch
unity-tech-cn:/hh-develop-water-balloon-fight
unity-tech-cn:/gc-hyper
unity-tech-cn:/layernorm
unity-tech-cn:/yamato-linux-debug-venv
unity-tech-cn:/soccer-comms
unity-tech-cn:/hh-develop-pushblockcollab
unity-tech-cn:/release_12_branch
unity-tech-cn:/fix-get-step-sp-curr
unity-tech-cn:/continuous-comms
unity-tech-cn:/no-comms
unity-tech-cn:/hh-develop-zombiepushblock
unity-tech-cn:/hypernetwork
unity-tech-cn:/revert-4859-develop-update-readme
unity-tech-cn:/sequencer-env-attention
unity-tech-cn:/hh-develop-variableobs
unity-tech-cn:/exp-tanh
unity-tech-cn:/reward-dist
unity-tech-cn:/exp-weight-decay
unity-tech-cn:/exp-robot
unity-tech-cn:/bullet-hell-barracuda-test-1.3.1
unity-tech-cn:/release_13_branch
unity-tech-cn:/release_14_branch
unity-tech-cn:/exp-clipped-gaussian-entropy
unity-tech-cn:/tic-tac-toe
unity-tech-cn:/hh-develop-dodgeball
unity-tech-cn:/repro-vis-obs-perf
unity-tech-cn:/v2-staging-rebase
unity-tech-cn:/release_15_branch
unity-tech-cn:/release_15_removeendepisode
unity-tech-cn:/release_16_branch
unity-tech-cn:/release_16_fix_gridsensor
unity-tech-cn:/ai-hw-2021
unity-tech-cn:/check-for-ModelOverriders
unity-tech-cn:/fix-grid-obs-shape-init
unity-tech-cn:/fix-gym-needs-reset
unity-tech-cn:/fix-resume-imi
unity-tech-cn:/release_17_branch
unity-tech-cn:/release_17_branch_gpu_test
unity-tech-cn:/colab-links
unity-tech-cn:/exp-continuous-div
unity-tech-cn:/release_17_branch_gpu_2
unity-tech-cn:/exp-diverse-behavior
unity-tech-cn:/grid-onehot-extra-dim-empty
unity-tech-cn:/2.0-verified
unity-tech-cn:/faster-entropy-coeficient-convergence
unity-tech-cn:/pre-r18-update-changelog
unity-tech-cn:/release_18_branch
unity-tech-cn:/main/tracking
unity-tech-cn:/main/reward-providers
unity-tech-cn:/main/project-upgrade
unity-tech-cn:/main/limitation-docs
unity-tech-cn:/develop/nomaxstep-test
unity-tech-cn:/develop/tf2.0
unity-tech-cn:/develop/tanhsquash
unity-tech-cn:/develop/magic-string
unity-tech-cn:/develop/trainerinterface
unity-tech-cn:/develop/separatevalue
unity-tech-cn:/develop/nopreviousactions
unity-tech-cn:/develop/reenablerepeatactions
unity-tech-cn:/develop/0memories
unity-tech-cn:/develop/fixmemoryleak
unity-tech-cn:/develop/reducewalljump
unity-tech-cn:/develop/removeactionholder-onehot
unity-tech-cn:/develop/canonicalize-quaternions
unity-tech-cn:/develop/self-playassym
unity-tech-cn:/develop/demo-load-seek
unity-tech-cn:/develop/progress-bar
unity-tech-cn:/develop/sac-apex
unity-tech-cn:/develop/cubewars
unity-tech-cn:/develop/add-fire
unity-tech-cn:/develop/gym-wrapper
unity-tech-cn:/develop/mm-docs-main-readme
unity-tech-cn:/develop/mm-docs-overview
unity-tech-cn:/develop/no-threading
unity-tech-cn:/develop/dockerfile
unity-tech-cn:/develop/model-store
unity-tech-cn:/develop/checkout-conversion-rebase
unity-tech-cn:/develop/model-transfer
unity-tech-cn:/develop/bisim-review
unity-tech-cn:/develop/taggedobservations
unity-tech-cn:/develop/transfer-bisim
unity-tech-cn:/develop/bisim-sac-transfer
unity-tech-cn:/develop/basketball
unity-tech-cn:/develop/torchmodules
unity-tech-cn:/develop/fixmarkdown
unity-tech-cn:/develop/shortenstrikervsgoalie
unity-tech-cn:/develop/shortengoalie
unity-tech-cn:/develop/torch-save-rp
unity-tech-cn:/develop/torch-to-np
unity-tech-cn:/develop/torch-omp-no-thread
unity-tech-cn:/develop/actionmodel-csharp
unity-tech-cn:/develop/torch-extra
unity-tech-cn:/develop/restructure-torch-networks
unity-tech-cn:/develop/jit
unity-tech-cn:/develop/adjust-cpu-settings-experiment
unity-tech-cn:/develop/torch-sac-threading
unity-tech-cn:/develop/wb
unity-tech-cn:/develop/amrl
unity-tech-cn:/develop/memorydump
unity-tech-cn:/develop/permutepytorch
unity-tech-cn:/develop/sac-targetq
unity-tech-cn:/develop/actions-out
unity-tech-cn:/develop/reshapeonnxmemories
unity-tech-cn:/develop/crawlergail
unity-tech-cn:/develop/debugtorchfood
unity-tech-cn:/develop/hybrid-actions
unity-tech-cn:/develop/bullet-hell
unity-tech-cn:/develop/action-spec-gym
unity-tech-cn:/develop/battlefoodcollector
unity-tech-cn:/develop/use-action-buffers
unity-tech-cn:/develop/hardswish
unity-tech-cn:/develop/leakyrelu
unity-tech-cn:/develop/torch-clip-scale
unity-tech-cn:/develop/contentropy
unity-tech-cn:/develop/manch
unity-tech-cn:/develop/torchcrawlerdebug
unity-tech-cn:/develop/fix-nan
unity-tech-cn:/develop/multitype-buffer
unity-tech-cn:/develop/windows-delay
unity-tech-cn:/develop/torch-tanh
unity-tech-cn:/develop/gail-norm
unity-tech-cn:/develop/multiprocess
unity-tech-cn:/develop/unified-obs
unity-tech-cn:/develop/rm-rf-new-models
unity-tech-cn:/develop/skipcritic
unity-tech-cn:/develop/centralizedcritic
unity-tech-cn:/develop/dodgeball-tests
unity-tech-cn:/develop/cc-teammanager
unity-tech-cn:/develop/weight-decay
unity-tech-cn:/develop/singular-embeddings
unity-tech-cn:/develop/zombieteammanager
unity-tech-cn:/develop/superpush
unity-tech-cn:/develop/teammanager
unity-tech-cn:/develop/zombie-exp
unity-tech-cn:/develop/update-readme
unity-tech-cn:/develop/readme-fix
unity-tech-cn:/develop/coma-noact
unity-tech-cn:/develop/coma-withq
unity-tech-cn:/develop/coma2
unity-tech-cn:/develop/action-slice
unity-tech-cn:/develop/gru
unity-tech-cn:/develop/critic-op-lstm-currentmem
unity-tech-cn:/develop/decaygail
unity-tech-cn:/develop/gail-srl-hack
unity-tech-cn:/develop/rear-pad
unity-tech-cn:/develop/mm-copyright-dates
unity-tech-cn:/develop/dodgeball-raycasts
unity-tech-cn:/develop/collab-envs-exp-ervin
unity-tech-cn:/develop/pushcollabonly
unity-tech-cn:/develop/sample-curation
unity-tech-cn:/develop/soccer-groupman
unity-tech-cn:/develop/input-actuator-tanks
unity-tech-cn:/develop/validate-release-fix
unity-tech-cn:/develop/new-console-log
unity-tech-cn:/develop/lex-walker-model
unity-tech-cn:/develop/lstm-burnin
unity-tech-cn:/develop/grid-vaiable-names
unity-tech-cn:/develop/fix-attn-embedding
unity-tech-cn:/develop/api-documentation-update-some-fixes
unity-tech-cn:/develop/update-grpc
unity-tech-cn:/develop/grid-rootref-debug
unity-tech-cn:/develop/pbcollab-rays
unity-tech-cn:/develop/2.0-verified-pre
unity-tech-cn:/develop/parameterizedenvs
unity-tech-cn:/develop/custom-ray-sensor
unity-tech-cn:/develop/mm-add-v2blog
unity-tech-cn:/develop/custom-raycast
unity-tech-cn:/develop/area-manager
unity-tech-cn:/develop/remove-unecessary-lr
unity-tech-cn:/develop/use-base-env-in-learn
unity-tech-cn:/soccer-fives/multiagent
unity-tech-cn:/develop/cubewars/splashdamage
unity-tech-cn:/develop/add-fire/exp
unity-tech-cn:/develop/add-fire/jit
unity-tech-cn:/develop/add-fire/speedtest
unity-tech-cn:/develop/add-fire/bc
unity-tech-cn:/develop/add-fire/ckpt-2
unity-tech-cn:/develop/add-fire/normalize-context
unity-tech-cn:/develop/add-fire/components-dir
unity-tech-cn:/develop/add-fire/halfentropy
unity-tech-cn:/develop/add-fire/memoryclass
unity-tech-cn:/develop/add-fire/categoricaldist
unity-tech-cn:/develop/add-fire/mm
unity-tech-cn:/develop/add-fire/sac-lst
unity-tech-cn:/develop/add-fire/mm3
unity-tech-cn:/develop/add-fire/continuous
unity-tech-cn:/develop/add-fire/ghost
unity-tech-cn:/develop/add-fire/policy-tests
unity-tech-cn:/develop/add-fire/export-discrete
unity-tech-cn:/develop/add-fire/test-simple-rl-fix-resnet
unity-tech-cn:/develop/add-fire/remove-currdoc
unity-tech-cn:/develop/add-fire/clean2
unity-tech-cn:/develop/add-fire/doc-cleanups
unity-tech-cn:/develop/add-fire/changelog
unity-tech-cn:/develop/add-fire/mm2
unity-tech-cn:/develop/model-transfer/add-physics
unity-tech-cn:/develop/model-transfer/train
unity-tech-cn:/develop/jit/experiments
unity-tech-cn:/exp-vince/sep30-2020
unity-tech-cn:/hh-develop-gridsensor-tests/static
unity-tech-cn:/develop/hybrid-actions/distlist
unity-tech-cn:/develop/bullet-hell/buffer
unity-tech-cn:/goal-conditioning/new
unity-tech-cn:/goal-conditioning/sensors-2
unity-tech-cn:/goal-conditioning/sensors-3-pytest-fix
unity-tech-cn:/goal-conditioning/grid-world
unity-tech-cn:/soccer-comms/disc
unity-tech-cn:/develop/centralizedcritic/counterfact
unity-tech-cn:/develop/centralizedcritic/mm
unity-tech-cn:/develop/centralizedcritic/nonego
unity-tech-cn:/develop/zombieteammanager/disableagent
unity-tech-cn:/develop/zombieteammanager/killfirst
unity-tech-cn:/develop/superpush/int
unity-tech-cn:/develop/superpush/branch-cleanup
unity-tech-cn:/develop/teammanager/int
unity-tech-cn:/develop/teammanager/cubewar-nocycle
unity-tech-cn:/develop/teammanager/cubewars
unity-tech-cn:/develop/superpush/int/hunter
unity-tech-cn:/goal-conditioning/new/allo-crawler
unity-tech-cn:/develop/coma2/clip
unity-tech-cn:/develop/coma2/singlenetwork
unity-tech-cn:/develop/coma2/samenet
unity-tech-cn:/develop/coma2/fixgroup
unity-tech-cn:/develop/coma2/samenet/sum
unity-tech-cn:/hh-develop-dodgeball/goy-input
unity-tech-cn:/develop/soccer-groupman/mod
unity-tech-cn:/develop/soccer-groupman/mod/hunter
unity-tech-cn:/develop/soccer-groupman/mod/hunter/cine
unity-tech-cn:/ai-hw-2021/tensor-applier
拉取从: unity-tech-cn:develop/parameterizedenvs
unity-tech-cn:/main
unity-tech-cn:/develop-generalizationTraining-TrainerController
unity-tech-cn:/tag-0.2.0
unity-tech-cn:/tag-0.2.1
unity-tech-cn:/tag-0.2.1a
unity-tech-cn:/tag-0.2.1c
unity-tech-cn:/tag-0.2.1d
unity-tech-cn:/hotfix-v0.9.2a
unity-tech-cn:/develop-gpu-test
unity-tech-cn:/0.10.1
unity-tech-cn:/develop-pyinstaller
unity-tech-cn:/develop-horovod
unity-tech-cn:/PhysXArticulations20201
unity-tech-cn:/importdocfix
unity-tech-cn:/develop-resizetexture
unity-tech-cn:/hh-develop-walljump_bugfixes
unity-tech-cn:/develop-walljump-fix-sac
unity-tech-cn:/hh-develop-walljump_rnd
unity-tech-cn:/tag-0.11.0.dev0
unity-tech-cn:/develop-pytorch
unity-tech-cn:/tag-0.11.0.dev2
unity-tech-cn:/develop-newnormalization
unity-tech-cn:/tag-0.11.0.dev3
unity-tech-cn:/develop
unity-tech-cn:/release-0.12.0
unity-tech-cn:/tag-0.12.0-dev
unity-tech-cn:/tag-0.12.0.dev0
unity-tech-cn:/tag-0.12.1
unity-tech-cn:/2D-explorations
unity-tech-cn:/asymm-envs
unity-tech-cn:/tag-0.12.1.dev0
unity-tech-cn:/2D-exploration-raycast
unity-tech-cn:/tag-0.12.1.dev1
unity-tech-cn:/release-0.13.0
unity-tech-cn:/release-0.13.1
unity-tech-cn:/plugin-proof-of-concept
unity-tech-cn:/release-0.14.0
unity-tech-cn:/hotfix-bump-version-master
unity-tech-cn:/soccer-fives
unity-tech-cn:/release-0.14.1
unity-tech-cn:/bug-failed-api-check
unity-tech-cn:/test-recurrent-gail
unity-tech-cn:/hh-add-icons
unity-tech-cn:/release-0.15.0
unity-tech-cn:/release-0.15.1
unity-tech-cn:/hh-develop-all-posed-characters
unity-tech-cn:/internal-policy-ghost
unity-tech-cn:/distributed-training
unity-tech-cn:/hh-develop-improve_tennis
unity-tech-cn:/test-tf-ver
unity-tech-cn:/release_1_branch
unity-tech-cn:/tennis-time-horizon
unity-tech-cn:/whitepaper-experiments
unity-tech-cn:/r2v-yamato-linux
unity-tech-cn:/docs-update
unity-tech-cn:/release_2_branch
unity-tech-cn:/exp-mede
unity-tech-cn:/sensitivity
unity-tech-cn:/release_2_verified_load_fix
unity-tech-cn:/test-sampler
unity-tech-cn:/release_2_verified
unity-tech-cn:/hh-develop-ragdoll-testing
unity-tech-cn:/origin-develop-taggedobservations
unity-tech-cn:/MLA-1734-demo-provider
unity-tech-cn:/sampler-refactor-copy
unity-tech-cn:/PhysXArticulations20201Package
unity-tech-cn:/tag-com.unity.ml-agents_1.0.8
unity-tech-cn:/release_3_branch
unity-tech-cn:/github-actions
unity-tech-cn:/release_3_distributed
unity-tech-cn:/fix-batch-tennis
unity-tech-cn:/distributed-ppo-sac
unity-tech-cn:/gridworld-custom-obs
unity-tech-cn:/hw20-segmentation
unity-tech-cn:/hh-develop-gamedev-demo
unity-tech-cn:/active-variablespeed
unity-tech-cn:/release_4_branch
unity-tech-cn:/fix-env-step-loop
unity-tech-cn:/release_5_branch
unity-tech-cn:/fix-walker
unity-tech-cn:/release_6_branch
unity-tech-cn:/hh-32-observation-crawler
unity-tech-cn:/trainer-plugin
unity-tech-cn:/hh-develop-max-steps-demo-recorder
unity-tech-cn:/hh-develop-loco-walker-variable-speed
unity-tech-cn:/exp-0002
unity-tech-cn:/experiment-less-max-step
unity-tech-cn:/hh-develop-hallway-wall-mesh-fix
unity-tech-cn:/release_7_branch
unity-tech-cn:/exp-vince
unity-tech-cn:/hh-develop-gridsensor-tests
unity-tech-cn:/tag-release_8_test0
unity-tech-cn:/tag-release_8_test1
unity-tech-cn:/release_8_branch
unity-tech-cn:/docfix-end-episode
unity-tech-cn:/release_9_branch
unity-tech-cn:/hybrid-action-rewardsignals
unity-tech-cn:/MLA-462-yamato-win
unity-tech-cn:/exp-alternate-atten
unity-tech-cn:/hh-develop-fps_game_project
unity-tech-cn:/fix-conflict-base-env
unity-tech-cn:/release_10_branch
unity-tech-cn:/exp-bullet-hell-trainer
unity-tech-cn:/ai-summit-exp
unity-tech-cn:/comms-grad
unity-tech-cn:/walljump-pushblock
unity-tech-cn:/goal-conditioning
unity-tech-cn:/release_11_branch
unity-tech-cn:/hh-develop-water-balloon-fight
unity-tech-cn:/gc-hyper
unity-tech-cn:/layernorm
unity-tech-cn:/yamato-linux-debug-venv
unity-tech-cn:/soccer-comms
unity-tech-cn:/hh-develop-pushblockcollab
unity-tech-cn:/release_12_branch
unity-tech-cn:/fix-get-step-sp-curr
unity-tech-cn:/continuous-comms
unity-tech-cn:/no-comms
unity-tech-cn:/hh-develop-zombiepushblock
unity-tech-cn:/hypernetwork
unity-tech-cn:/revert-4859-develop-update-readme
unity-tech-cn:/sequencer-env-attention
unity-tech-cn:/hh-develop-variableobs
unity-tech-cn:/exp-tanh
unity-tech-cn:/reward-dist
unity-tech-cn:/exp-weight-decay
unity-tech-cn:/exp-robot
unity-tech-cn:/bullet-hell-barracuda-test-1.3.1
unity-tech-cn:/release_13_branch
unity-tech-cn:/release_14_branch
unity-tech-cn:/exp-clipped-gaussian-entropy
unity-tech-cn:/tic-tac-toe
unity-tech-cn:/hh-develop-dodgeball
unity-tech-cn:/repro-vis-obs-perf
unity-tech-cn:/v2-staging-rebase
unity-tech-cn:/release_15_branch
unity-tech-cn:/release_15_removeendepisode
unity-tech-cn:/release_16_branch
unity-tech-cn:/release_16_fix_gridsensor
unity-tech-cn:/ai-hw-2021
unity-tech-cn:/check-for-ModelOverriders
unity-tech-cn:/fix-grid-obs-shape-init
unity-tech-cn:/fix-gym-needs-reset
unity-tech-cn:/fix-resume-imi
unity-tech-cn:/release_17_branch
unity-tech-cn:/release_17_branch_gpu_test
unity-tech-cn:/colab-links
unity-tech-cn:/exp-continuous-div
unity-tech-cn:/release_17_branch_gpu_2
unity-tech-cn:/exp-diverse-behavior
unity-tech-cn:/grid-onehot-extra-dim-empty
unity-tech-cn:/2.0-verified
unity-tech-cn:/faster-entropy-coeficient-convergence
unity-tech-cn:/pre-r18-update-changelog
unity-tech-cn:/release_18_branch
unity-tech-cn:/main/tracking
unity-tech-cn:/main/reward-providers
unity-tech-cn:/main/project-upgrade
unity-tech-cn:/main/limitation-docs
unity-tech-cn:/develop/nomaxstep-test
unity-tech-cn:/develop/tf2.0
unity-tech-cn:/develop/tanhsquash
unity-tech-cn:/develop/magic-string
unity-tech-cn:/develop/trainerinterface
unity-tech-cn:/develop/separatevalue
unity-tech-cn:/develop/nopreviousactions
unity-tech-cn:/develop/reenablerepeatactions
unity-tech-cn:/develop/0memories
unity-tech-cn:/develop/fixmemoryleak
unity-tech-cn:/develop/reducewalljump
unity-tech-cn:/develop/removeactionholder-onehot
unity-tech-cn:/develop/canonicalize-quaternions
unity-tech-cn:/develop/self-playassym
unity-tech-cn:/develop/demo-load-seek
unity-tech-cn:/develop/progress-bar
unity-tech-cn:/develop/sac-apex
unity-tech-cn:/develop/cubewars
unity-tech-cn:/develop/add-fire
unity-tech-cn:/develop/gym-wrapper
unity-tech-cn:/develop/mm-docs-main-readme
unity-tech-cn:/develop/mm-docs-overview
unity-tech-cn:/develop/no-threading
unity-tech-cn:/develop/dockerfile
unity-tech-cn:/develop/model-store
unity-tech-cn:/develop/checkout-conversion-rebase
unity-tech-cn:/develop/model-transfer
unity-tech-cn:/develop/bisim-review
unity-tech-cn:/develop/taggedobservations
unity-tech-cn:/develop/transfer-bisim
unity-tech-cn:/develop/bisim-sac-transfer
unity-tech-cn:/develop/basketball
unity-tech-cn:/develop/torchmodules
unity-tech-cn:/develop/fixmarkdown
unity-tech-cn:/develop/shortenstrikervsgoalie
unity-tech-cn:/develop/shortengoalie
unity-tech-cn:/develop/torch-save-rp
unity-tech-cn:/develop/torch-to-np
unity-tech-cn:/develop/torch-omp-no-thread
unity-tech-cn:/develop/actionmodel-csharp
unity-tech-cn:/develop/torch-extra
unity-tech-cn:/develop/restructure-torch-networks
unity-tech-cn:/develop/jit
unity-tech-cn:/develop/adjust-cpu-settings-experiment
unity-tech-cn:/develop/torch-sac-threading
unity-tech-cn:/develop/wb
unity-tech-cn:/develop/amrl
unity-tech-cn:/develop/memorydump
unity-tech-cn:/develop/permutepytorch
unity-tech-cn:/develop/sac-targetq
unity-tech-cn:/develop/actions-out
unity-tech-cn:/develop/reshapeonnxmemories
unity-tech-cn:/develop/crawlergail
unity-tech-cn:/develop/debugtorchfood
unity-tech-cn:/develop/hybrid-actions
unity-tech-cn:/develop/bullet-hell
unity-tech-cn:/develop/action-spec-gym
unity-tech-cn:/develop/battlefoodcollector
unity-tech-cn:/develop/use-action-buffers
unity-tech-cn:/develop/hardswish
unity-tech-cn:/develop/leakyrelu
unity-tech-cn:/develop/torch-clip-scale
unity-tech-cn:/develop/contentropy
unity-tech-cn:/develop/manch
unity-tech-cn:/develop/torchcrawlerdebug
unity-tech-cn:/develop/fix-nan
unity-tech-cn:/develop/multitype-buffer
unity-tech-cn:/develop/windows-delay
unity-tech-cn:/develop/torch-tanh
unity-tech-cn:/develop/gail-norm
unity-tech-cn:/develop/multiprocess
unity-tech-cn:/develop/unified-obs
unity-tech-cn:/develop/rm-rf-new-models
unity-tech-cn:/develop/skipcritic
unity-tech-cn:/develop/centralizedcritic
unity-tech-cn:/develop/dodgeball-tests
unity-tech-cn:/develop/cc-teammanager
unity-tech-cn:/develop/weight-decay
unity-tech-cn:/develop/singular-embeddings
unity-tech-cn:/develop/zombieteammanager
unity-tech-cn:/develop/superpush
unity-tech-cn:/develop/teammanager
unity-tech-cn:/develop/zombie-exp
unity-tech-cn:/develop/update-readme
unity-tech-cn:/develop/readme-fix
unity-tech-cn:/develop/coma-noact
unity-tech-cn:/develop/coma-withq
unity-tech-cn:/develop/coma2
unity-tech-cn:/develop/action-slice
unity-tech-cn:/develop/gru
unity-tech-cn:/develop/critic-op-lstm-currentmem
unity-tech-cn:/develop/decaygail
unity-tech-cn:/develop/gail-srl-hack
unity-tech-cn:/develop/rear-pad
unity-tech-cn:/develop/mm-copyright-dates
unity-tech-cn:/develop/dodgeball-raycasts
unity-tech-cn:/develop/collab-envs-exp-ervin
unity-tech-cn:/develop/pushcollabonly
unity-tech-cn:/develop/sample-curation
unity-tech-cn:/develop/soccer-groupman
unity-tech-cn:/develop/input-actuator-tanks
unity-tech-cn:/develop/validate-release-fix
unity-tech-cn:/develop/new-console-log
unity-tech-cn:/develop/lex-walker-model
unity-tech-cn:/develop/lstm-burnin
unity-tech-cn:/develop/grid-vaiable-names
unity-tech-cn:/develop/fix-attn-embedding
unity-tech-cn:/develop/api-documentation-update-some-fixes
unity-tech-cn:/develop/update-grpc
unity-tech-cn:/develop/grid-rootref-debug
unity-tech-cn:/develop/pbcollab-rays
unity-tech-cn:/develop/2.0-verified-pre
unity-tech-cn:/develop/parameterizedenvs
unity-tech-cn:/develop/custom-ray-sensor
unity-tech-cn:/develop/mm-add-v2blog
unity-tech-cn:/develop/custom-raycast
unity-tech-cn:/develop/area-manager
unity-tech-cn:/develop/remove-unecessary-lr
unity-tech-cn:/develop/use-base-env-in-learn
unity-tech-cn:/soccer-fives/multiagent
unity-tech-cn:/develop/cubewars/splashdamage
unity-tech-cn:/develop/add-fire/exp
unity-tech-cn:/develop/add-fire/jit
unity-tech-cn:/develop/add-fire/speedtest
unity-tech-cn:/develop/add-fire/bc
unity-tech-cn:/develop/add-fire/ckpt-2
unity-tech-cn:/develop/add-fire/normalize-context
unity-tech-cn:/develop/add-fire/components-dir
unity-tech-cn:/develop/add-fire/halfentropy
unity-tech-cn:/develop/add-fire/memoryclass
unity-tech-cn:/develop/add-fire/categoricaldist
unity-tech-cn:/develop/add-fire/mm
unity-tech-cn:/develop/add-fire/sac-lst
unity-tech-cn:/develop/add-fire/mm3
unity-tech-cn:/develop/add-fire/continuous
unity-tech-cn:/develop/add-fire/ghost
unity-tech-cn:/develop/add-fire/policy-tests
unity-tech-cn:/develop/add-fire/export-discrete
unity-tech-cn:/develop/add-fire/test-simple-rl-fix-resnet
unity-tech-cn:/develop/add-fire/remove-currdoc
unity-tech-cn:/develop/add-fire/clean2
unity-tech-cn:/develop/add-fire/doc-cleanups
unity-tech-cn:/develop/add-fire/changelog
unity-tech-cn:/develop/add-fire/mm2
unity-tech-cn:/develop/model-transfer/add-physics
unity-tech-cn:/develop/model-transfer/train
unity-tech-cn:/develop/jit/experiments
unity-tech-cn:/exp-vince/sep30-2020
unity-tech-cn:/hh-develop-gridsensor-tests/static
unity-tech-cn:/develop/hybrid-actions/distlist
unity-tech-cn:/develop/bullet-hell/buffer
unity-tech-cn:/goal-conditioning/new
unity-tech-cn:/goal-conditioning/sensors-2
unity-tech-cn:/goal-conditioning/sensors-3-pytest-fix
unity-tech-cn:/goal-conditioning/grid-world
unity-tech-cn:/soccer-comms/disc
unity-tech-cn:/develop/centralizedcritic/counterfact
unity-tech-cn:/develop/centralizedcritic/mm
unity-tech-cn:/develop/centralizedcritic/nonego
unity-tech-cn:/develop/zombieteammanager/disableagent
unity-tech-cn:/develop/zombieteammanager/killfirst
unity-tech-cn:/develop/superpush/int
unity-tech-cn:/develop/superpush/branch-cleanup
unity-tech-cn:/develop/teammanager/int
unity-tech-cn:/develop/teammanager/cubewar-nocycle
unity-tech-cn:/develop/teammanager/cubewars
unity-tech-cn:/develop/superpush/int/hunter
unity-tech-cn:/goal-conditioning/new/allo-crawler
unity-tech-cn:/develop/coma2/clip
unity-tech-cn:/develop/coma2/singlenetwork
unity-tech-cn:/develop/coma2/samenet
unity-tech-cn:/develop/coma2/fixgroup
unity-tech-cn:/develop/coma2/samenet/sum
unity-tech-cn:/hh-develop-dodgeball/goy-input
unity-tech-cn:/develop/soccer-groupman/mod
unity-tech-cn:/develop/soccer-groupman/mod/hunter
unity-tech-cn:/develop/soccer-groupman/mod/hunter/cine
unity-tech-cn:/ai-hw-2021/tensor-applier
此合并请求有变更与目标分支冲突。
/DevProject/Packages/packages-lock.json
/utils/make_readme_table.py
/.yamato/com.unity.ml-agents-test.yml
/gym-unity/gym_unity/envs/__init__.py
/gym-unity/gym_unity/__init__.py
/Project/Packages/packages-lock.json
/Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/ModelOverrider.cs
/Project/Assets/ML-Agents/Examples/Soccer/Prefabs/SoccerFieldTwos.prefab
/com.unity.ml-agents.extensions/package.json
/com.unity.ml-agents.extensions/Documentation~/com.unity.ml-agents.extensions.md
/com.unity.ml-agents/package.json
/com.unity.ml-agents/Documentation~/com.unity.ml-agents.md
/com.unity.ml-agents/Tests/Runtime/Sensor/BoxOverlapCheckerTests.cs
/com.unity.ml-agents/Runtime/Academy.cs
/com.unity.ml-agents/Runtime/Actuators/IActionReceiver.cs
/com.unity.ml-agents/Runtime/Actuators/IDiscreteActionMask.cs
/com.unity.ml-agents/Runtime/Agent.cs
/com.unity.ml-agents/Runtime/Demonstrations/DemonstrationRecorder.cs
/com.unity.ml-agents/Runtime/Integrations/Match3/Match3SensorComponent.cs
/com.unity.ml-agents/Runtime/Sensors/BoxOverlapChecker.cs
/com.unity.ml-agents/Runtime/Sensors/GridSensorComponent.cs
/com.unity.ml-agents/CHANGELOG.md
/ml-agents-envs/README.md
/ml-agents-envs/mlagents_envs/__init__.py
/docs/Installation-Anaconda-Windows.md
/docs/Installation.md
/docs/Learning-Environment-Design-Agents.md
/docs/Migrating.md
/docs/Training-on-Amazon-Web-Service.md
/docs/Training-on-Microsoft-Azure.md
/docs/Unity-Inference-Engine.md
/ml-agents/setup.py
/ml-agents/README.md
/ml-agents/mlagents/trainers/settings.py
/ml-agents/mlagents/trainers/tests/test_stats.py
/ml-agents/mlagents/trainers/__init__.py
/README.md
3 次代码提交
作者 | SHA1 | 备注 | 提交日期 |
---|---|---|---|
Scott | 97990611 | Added decision frequency and evaluation metric | 4 年前 |
Scott | 130512b4 | fixed episode length modification issue. | 4 年前 |
Scott | aab3a80e |
Added version of 3D ball to use environment parameters
Can spawn a variable number of environments, change episode length, and reward type using environment parameters. |
4 年前 |
共有 78 个文件被更改,包括 2911 次插入 和 167 次删除
-
4DevProject/Packages/packages-lock.json
-
1utils/make_readme_table.py
-
2.yamato/com.unity.ml-agents-coverage.yml
-
2.yamato/com.unity.ml-agents-test.yml
-
4gym-unity/gym_unity/__init__.py
-
9gym-unity/gym_unity/envs/__init__.py
-
21gym-unity/gym_unity/tests/test_gym.py
-
12README.md
-
13com.unity.ml-agents.extensions/Documentation~/com.unity.ml-agents.extensions.md
-
2com.unity.ml-agents.extensions/package.json
-
2com.unity.ml-agents/package.json
-
11com.unity.ml-agents/CHANGELOG.md
-
14com.unity.ml-agents/Documentation~/com.unity.ml-agents.md
-
8com.unity.ml-agents/Editor/Match3ActuatorComponentEditor.cs
-
8com.unity.ml-agents/Editor/Match3SensorComponentEditor.cs
-
1com.unity.ml-agents/Editor/GridSensorComponentEditor.cs
-
4com.unity.ml-agents/Runtime/Academy.cs
-
2com.unity.ml-agents/Runtime/Actuators/IActionReceiver.cs
-
2com.unity.ml-agents/Runtime/Actuators/IDiscreteActionMask.cs
-
26com.unity.ml-agents/Runtime/Agent.cs
-
2com.unity.ml-agents/Runtime/Demonstrations/DemonstrationRecorder.cs
-
6com.unity.ml-agents/Runtime/Integrations/Match3/Match3ActuatorComponent.cs
-
4com.unity.ml-agents/Runtime/Integrations/Match3/Match3SensorComponent.cs
-
21com.unity.ml-agents/Runtime/Sensors/BoxOverlapChecker.cs
-
13com.unity.ml-agents/Runtime/Sensors/GridSensorComponent.cs
-
9com.unity.ml-agents/Tests/Editor/Integrations/Match3/Match3ActuatorTests.cs
-
9com.unity.ml-agents/Tests/Editor/Integrations/Match3/Match3SensorTests.cs
-
28com.unity.ml-agents/Tests/Runtime/Sensor/BoxOverlapCheckerTests.cs
-
2ml-agents-envs/README.md
-
4ml-agents-envs/mlagents_envs/__init__.py
-
8docs/Installation-Anaconda-Windows.md
-
8docs/Installation.md
-
2docs/Training-on-Amazon-Web-Service.md
-
2docs/Training-on-Microsoft-Azure.md
-
4docs/Unity-Inference-Engine.md
-
19docs/Learning-Environment-Design-Agents.md
-
32docs/Migrating.md
-
2ml-agents/setup.py
-
2ml-agents/README.md
-
1ml-agents/mlagents/plugins/stats_writer.py
-
15ml-agents/mlagents/trainers/stats.py
-
4ml-agents/mlagents/trainers/__init__.py
-
11ml-agents/mlagents/trainers/torch/networks.py
-
35ml-agents/mlagents/trainers/settings.py
-
25ml-agents/mlagents/trainers/tests/test_stats.py
-
35ml-agents/mlagents/trainers/tests/test_settings.py
-
2ml-agents/mlagents/trainers/tests/test_trainer_util.py
-
1ml-agents/mlagents/trainers/trainer/rl_trainer.py
-
5ml-agents/mlagents/trainers/trainer/trainer_factory.py
-
4Project/Packages/packages-lock.json
-
8Project/Assets/ML-Agents/Examples/Soccer/Prefabs/SoccerFieldTwos.prefab
-
6Project/Assets/ML-Agents/Examples/Soccer/Prefabs/StrikersVsGoalieField.prefab
-
54Project/Assets/ML-Agents/Examples/PushBlock/Prefabs/PushBlockCollabAreaGrid.prefab
-
5Project/Assets/ML-Agents/Examples/PushBlock/Scenes/PushBlockCollab.unity
-
4Project/Assets/ML-Agents/Examples/Match3/Scripts/Match3Drawer.cs
-
6Project/Assets/ML-Agents/Examples/Match3/Scripts/Match3Agent.cs
-
136Project/Assets/ML-Agents/Examples/FoodCollector/Prefabs/VisualFoodCollectorArea.prefab
-
12Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/ModelOverrider.cs
-
13Project/Assets/ML-Agents/Examples/SharedAssets/Materials/Checkers_Gray.mat
-
76com.unity.ml-agents.extensions/Documentation~/CustomGridSensors.md
-
303DBallMultiPower.yaml
-
335Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallMultiPower.onnx
-
14Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallMultiPower.onnx.meta
-
7Project/Assets/ML-Agents/Examples/3DBall/Prefabs/3DBallAgentArea.prefab.meta
-
7Project/Assets/ML-Agents/Examples/3DBall/Prefabs/3DBallMulti.prefab.meta
-
52Project/Assets/ML-Agents/Examples/3DBall/Prefabs/3DBallAgentArea.prefab
-
840Project/Assets/ML-Agents/Examples/3DBall/Prefabs/3DBallMulti.prefab
-
7Project/Assets/ML-Agents/Examples/3DBall/Scenes/3DBallMulti.unity.meta
-
560Project/Assets/ML-Agents/Examples/3DBall/Scenes/3DBallMulti.unity
-
11Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DAgentArea.cs.meta
-
11Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DMultiAgent.cs.meta
-
9Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DRewardTypes.cs
-
11Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DRewardTypes.cs.meta
-
127Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DAgentArea.cs
-
178Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DMultiAgent.cs
-
32config/ppo/3DBallMulti_distance.yaml
-
32config/ppo/3DBallMulti_power.yaml
-
32config/ppo/3DBallMulti_time.yaml
|
|||
# Version of the library that will be used to upload to pypi |
|||
__version__ = "0.26.0.dev0" |
|||
__version__ = "0.26.0" |
|||
__release_tag__ = None |
|||
__release_tag__ = "release_17" |
|
|||
# Version of the library that will be used to upload to pypi |
|||
__version__ = "0.26.0.dev0" |
|||
__version__ = "0.26.0" |
|||
__release_tag__ = None |
|||
__release_tag__ = "release_17" |
|
|||
# Version of the library that will be used to upload to pypi |
|||
__version__ = "0.26.0.dev0" |
|||
__version__ = "0.26.0" |
|||
__release_tag__ = None |
|||
__release_tag__ = "release_17" |
|
|||
# Extending Grid Sensors |
|||
|
|||
## Overview |
|||
Grid Sensor provides a 2D observation that detects objects around an agent from a top-down view. Compared to RayCasts, it receives a full observation in a grid area without gaps, and the detection is not blocked by objects around the agents. This gives a more granular view while requiring a higher usage of compute resources. |
|||
|
|||
One extra feature with Grid Sensors is that you can derive from the Grid Sensor base class to collect custom data besides the object tags, to include custom attributes as observations. This allows more flexibility for the use of GridSensor. This doc will elaborate how to create custom grid-based sensor class, and the sensors implementations provided in ml-agents package. |
|||
|
|||
## Customized Grid Sensor |
|||
To create a custom grid sensor, you'll need to derive from two classes: `GridSensorBase` and `GridSensorComponent`. |
|||
|
|||
### Deriving from `GridSensorBase` |
|||
This is the implementation of your sensor. This defines how your sensor process detected colliders, |
|||
what the data looks like, and how the observations are constructed from the detected objects. |
|||
Consider overriding the following methods depending on your use case: |
|||
* `protected virtual int GetCellObservationSize()`: Return the observation size per cell. Default to `1`. |
|||
* `protected virtual void GetObjectData(GameObject detectedObject, int tagIndex, float[] dataBuffer)`: Constructs observations from the detected object. The input provides the detected GameObject and the index of its tag (0-indexed). The observations should be written to the given `dataBuffer` and the buffer size is defined in `GetCellObservationSize()`. This data will be gathered from each cell and sent to the trainer as observation. |
|||
* `protected virtual bool IsDataNormalized()`: Return whether the observation is normalized to 0~1. This affects whether you're able to use compressed observations as compressed data only supports normalized data. Return `true` if all the values written in `GetObjectData` are within the range of (0, 1), otherwise return `false`. Default to `false`. |
|||
|
|||
There might be cases when your data is not in the range of (0, 1) but you still wish to use compressed data to speed up training. If your data is naturally bounded within a range, normalize your data first to the possible range and fill the buffer with normalized data. For example, since the angle of rotation is bounded within `0 ~ 360`, record an angle `x` as `x/360` instead of `x`. If your data value is not bounded (position, velocity, etc.), consider setting a reasonable min/max value and use that to normalize your data. |
|||
* `protected internal virtual ProcessCollidersMethod GetProcessCollidersMethod()`: Return the method to process colliders detected in a cell. This defines the sensor behavior when multiple objects with detectable tags are detected within a cell. |
|||
Currently two methods are provided: |
|||
* `ProcessCollidersMethod.ProcessClosestColliders` (Default): Process the closest collider to the agent. In this case each cell's data is represented by one object. |
|||
* `ProcessCollidersMethod.ProcessAllColliders`: Process all detected colliders. This is useful when the data from each cell is additive, for instance, the count of detected objects in a cell. When using this option, the input `dataBuffer` in `GetObjectData()` will contain processed data from other colliders detected in the cell. You'll more likely want to add/subtract values from the buffer instead of overwrite it completely. |
|||
|
|||
|
|||
### Deriving from `GridSensorComponent` |
|||
To create your sensor, you need to override the sensor component and add your sensor to the creation. |
|||
Specifically, you need to override `GetGridSensors()` and return an array of grid sensors you want to use in the component. |
|||
It can be used to create multiple different customized grid sensors, or you can also include the ones provided in our package (listed in the next section). |
|||
|
|||
Example: |
|||
``` |
|||
public class CustomGridSensorComponent : GridSensorComponent |
|||
{ |
|||
protected override GridSensorBase[] GetGridSensors() |
|||
{ |
|||
return new GridSensorBase[] { new CustomGridSensor(...)}; |
|||
} |
|||
} |
|||
``` |
|||
|
|||
## Grid Sensor Types |
|||
Here we list out two types of grid sensor we provide in our package: `OneHotGridSensor` and `CountingGridSensor`. |
|||
Their implementations are also a good reference for making you own ones. |
|||
|
|||
### OneHotGridSensor (provided in `com.unity.ml-agents`) |
|||
This is the default sensor used by `GridSensorComponent`. It detects objects with detectable tags and the observation is the one-hot representation of the detected tag index. |
|||
|
|||
The implementation of the sensor is defined as following: |
|||
* `GetCellObservationSize()`: `detectableTags.Length` |
|||
* `IsDataNormalized()`: `true` |
|||
* `ProcessCollidersMethod()`: `ProcessCollidersMethod.ProcessClosestColliders` |
|||
* `GetObjectData()`: |
|||
|
|||
``` |
|||
protected override void GetObjectData(GameObject detectedObject, int tagIndex, float[] dataBuffer) |
|||
{ |
|||
dataBuffer[tagIndex] = 1; |
|||
} |
|||
``` |
|||
|
|||
### CountingGridSensor (provided in `com.unity.ml-agents.extensions`) |
|||
This is an example of using all colliders detected in a cell. It counts the number of objects detected for each detectable tag. The sensor cannot be used with data compression. |
|||
|
|||
The implementation of the sensor is defined as following: |
|||
* `GetCellObservationSize()`: `detectableTags.Length` |
|||
* `IsDataNormalized()`: `false` |
|||
* `ProcessCollidersMethod()`: `ProcessCollidersMethod.ProcessAllColliders` |
|||
* `GetObjectData()`: |
|||
|
|||
``` |
|||
protected override void GetObjectData(GameObject detectedObject, int tagIndex, float[] dataBuffer) |
|||
{ |
|||
dataBuffer[tagIndex] += 1; |
|||
} |
|||
``` |
|
|||
behaviors: |
|||
3DBall: |
|||
trainer_type: ppo |
|||
hyperparameters: |
|||
batch_size: 64 |
|||
buffer_size: 12000 |
|||
learning_rate: 0.0003 |
|||
beta: 0.001 |
|||
epsilon: 0.2 |
|||
lambd: 0.99 |
|||
num_epoch: 3 |
|||
learning_rate_schedule: linear |
|||
network_settings: |
|||
normalize: true |
|||
hidden_units: 128 |
|||
num_layers: 2 |
|||
vis_encode_type: simple |
|||
reward_signals: |
|||
extrinsic: |
|||
gamma: 0.99 |
|||
strength: 1.0 |
|||
keep_checkpoints: 5 |
|||
max_steps: 500000 |
|||
time_horizon: 1000 |
|||
summary_freq: 12000 |
|||
|
|||
# Add this section |
|||
environment_parameters: |
|||
maxStep: 1000 |
|||
|
|
|||
pytorch1.8:�� |
|||
^ |
|||
obs_0 |
|||
Enetwork_body.observation_encoder.processors.0.normalizer.running_mean19Sub_0"Sub |
|||
|
|||
19 |
|||
4623Div_1"Div |
|||
4 |
|||
2324Clip_2"Clip* |
|||
max �@�* |
|||
min ��� |
|||
' |
|||
2425Concat_3"Concat* |
|||
axis� |
|||
� |
|||
25 |
|||
.network_body._body_endoder.seq_layers.0.weight |
|||
,network_body._body_endoder.seq_layers.0.bias26Gemm_4"Gemm* |
|||
alpha �?�* |
|||
beta �?�* |
|||
transB� |
|||
|
|||
2627 Sigmoid_5"Sigmoid |
|||
|
|||
26 |
|||
2728Mul_6"Mul |
|||
� |
|||
28 |
|||
.network_body._body_endoder.seq_layers.2.weight |
|||
,network_body._body_endoder.seq_layers.2.bias29Gemm_7"Gemm* |
|||
alpha �?�* |
|||
beta �?�* |
|||
transB� |
|||
|
|||
2930 Sigmoid_8"Sigmoid |
|||
|
|||
29 |
|||
3031Mul_9"Mul |
|||
� |
|||
31 |
|||
/action_model._continuous_distribution.mu.weight |
|||
-action_model._continuous_distribution.mu.bias32Gemm_10"Gemm* |
|||
alpha �?�* |
|||
beta �?�* |
|||
transB� |
|||
133Constant_11"Constant* |
|||
value*J � |
|||
|
|||
32 |
|||
3334Mul_12"Mul |
|||
F |
|||
34 |
|||
/action_model._continuous_distribution.log_sigma35Add_13"Add |
|||
|
|||
3536Exp_14"Exp |
|||
= |
|||
3237RandomNormalLike_15"RandomNormalLike* |
|||
dtype� |
|||
|
|||
37 |
|||
3638Mul_16"Mul |
|||
|
|||
32 |
|||
3839Add_17"Add |
|||
5 |
|||
3940Clip_18"Clip* |
|||
max @@�* |
|||
min @�� |
|||
) |
|||
40 |
|||
47continuous_actionsDiv_19"Divtorch-jit-export*Bversion_numberJ @@**Bcontinuous_action_output_shapeJ @*Bmemory_sizeJ *mBEnetwork_body.observation_encoder.processors.0.normalizer.running_meanJ ���s}G��^��r��=!�K����;�y��V _�*� �B.network_body._body_endoder.seq_layers.0.weightJ� �c��~�=CI�=��"��N��Q�;2Ӿk=>�B��ܘ�MܾF\��v.���4�><.�>9��~=w��Zz=�>�>�D7�E��=��>��=��>ݸž1� ?���u�i�}�d2�����?�>��?X�d�@'>JBq����='��=Cּe
y���=�%��d�?��ջ��4=V�*>\?��!>�lT<l��=F�M>��L?E���q��=nB�>?�>��,>�d��}QL��2��b�=V@?��> �x���<>���>�4>>����?&��[]?Ø |
|||
��b�>d����0�N;�<���>a�T��e%=X�R?����"�þ�� ?��H� 6����&?(��=dہ�>���?>\�ŽW[��刪�ޮ;�a��,>~z�>
�?���>ϔ뽛e>�h>�u�>�c�=�����j>H�!>�,��$?ZrI>c��>&~y>��"?����{����D���>��?�K�\S�>�^R�wƐ�.);=^�����C,�>��>��=�\]�>~�\��>G����>bl4�E�����<&�B>^,F�)�}��W�>lL>����ݥ=l[�>h)=_2��_�1>��$� sP>*��������>�.\?�?(\��J�? ?����3"y��%�=s+�:�>�4�<��x�@I&>�k>�ȥ=p^<?k���$�>�?!N?��*���=�1}>M��=y/m>�\����==&�Ⱦ�9⾕��>����t�y���G�E��b-g=,���U��;{}2�ƈ��L��i�ܾ�HT��2/>S�>�Ch?�l�=���<_s���
��<���ʊ>ѽ���~>_e>����.{�>���>1��=�H;lwQ?�>K�u?v����=��>)��<�{�>%�+>�a�Qpw�־�ܐ>���&P[����Mjb�:՞�N�8>��K�N?���>���>3v���ܺ<�P�>�c>Wh
��W����&�s;��{�0��=�m�>���??��`>���Zc��.�>j�������>�1?�>�w5>���>�&(�ܫ��Ū? 3��5~,?�i��&V��H/?F%3=Ś��3G�DA>�����^�V���*�8�U�r���`�(���T�>;x���p��e?!o����;���==�}��>n�<L�?>>�/���������>�Y�>�Y;��>8(>�&� =��V�>�h=��$= �g>����u�>�� |
|||
�y~���a��.���H����=��>4k�<�;�� |
|||
��2��>��?�0X>���>��>��>����K=�En�E�ɷ�BI"�"TP?~m��,xоel¾�UB>�����I�>}_>�}?|�<>G��=i��>q��� {7�p X>y�ҽ�&�>�����3ʻsӍ< ۀ�V`����������=�0?�@�6û�}��w��>l�־늾��>�t�`-=Cx=m�>������=�ƾ�c
?���=]x ���;�ǭ߾Ԭ*�Y��>�k��Y#��%�#���>����3'� F��n3�g`��,i�����s4��ۚv�w�������:��6F�=�K>{8��V.,>X�!�J��1�;�v=>�b >�V����=:�>��>҄>���/����t?̊�>Сb�N7����=�4�=č����>�� ?��ҾZ)�>�{��X�����<�?��V��9���5 >+�U��[[>cD8��?,�Z'?���=�@�=��1>� ?�>���=�)m�끅�: |
|||
|
|||
�5�$?ő?�z��<ž�#�>�0~=�C�>Lj�>GqA=���>ub>��
?�7�>��ѽ����\�>퐱>�l��OI�l��=p�*�������ߚ{�i[�>�Ш>�]>ž{>����h�>*�?e�ݼ6d�>�#?�z���O>�mǾ�X���R?�.���F�> �>"�e> z�>m��>o��=K,`��^f>�����G">$�{>z�����T��N[�J�C�i_G?c�d>}�G��b���@Y=~��=��������w> |
|||
�[?WJ=?1�?R+�>Q�0>c�[���ν��:?Z1d�!b�=���=��>̀k=��O����=^�>%R>?�>�l |
|||
>[>��>�<�>qJ��q\�q�~>t���,>Q���Ub������╾�>���(-?���Gz>��> |